Decision Analysis by Scenario Trees
Jun Feng · 2000
The main goal of this paper is to intrduce a new approach to represent and solve Bayesian decision problems—scenario trees.The solving method is called the pruning method.In scenario trees,the conditional probability for each edge emanating from a chance node is not needed.Instead,a joint probability for each path from the root node to a leaf node is required.The pruning method for scenario tree solutions is illustrated by a real world case.Finally,the comparison of scenrtio trees to decision trees is made.